© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 10578
    Prev
    Next
    INDEX
    Explanations

    phrases related to security and data protection in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.06
    2:0.08
    3:0.07
    4:0.08
    5:0.05
    6:0.10
    7:0.07
    8:0.04
    9:0.06
    10:0.08
    11:0.10
    Negative Logits
    arial
    -2.93
    kees
    -2.85
    RPG
    -2.83
    �
    -2.74
     Albania
    -2.72
     Tolkien
    -2.71
    Collins
    -2.71
     Randolph
    -2.67
     Chair
    -2.65
     Collins
    -2.65
    POSITIVE LOGITS
     firmware
    7.44
     Firm
    5.75
     FW
    4.04
    irm
    3.81
     kernel
    3.76
    kernel
    3.64
     BIOS
    3.50
    ernels
    3.48
     kernels
    3.46
     Kernel
    3.41
    Activations Density 0.004%

    No Known Activations